138 citations · 537 across the 23 of their papers we have counts for
24 papers
Riemannian Optimization in Modular Systems
Christian Pehle, Jean-Jacques Slotine
Understanding how systems built out of modular components can be jointly optimized is an important problem in biology, engineering, and machine learning. The backpropagation algori…
Bullet Trains: Parallelizing Training of Temporally Precise Spiking Neural Networks
Todd Morrill, Christian Pehle, Anthony Zador
Continuous-time, event-native spiking neural networks (SNNs) operate strictly on spike events, treating spike timing and ordering as the representation rather than an artifact of t…
Unlocked Backpropagation using Wave Scattering
Christian Pehle, Jean-Jacques Slotine
Both the backpropagation algorithm in machine learning and the maximum principle in optimal control theory are posed as a two-point boundary problem, resulting in a "forward-backwa…
Walking the Weight Manifold: a Topological Approach to Conditioning Inspired by Neuromodulation
Ari S. Benjamin, Kyle Daruwalla, Christian Pehle +2
One frequently wishes to learn a range of similar tasks as efficiently as possible, re-using knowledge across tasks. In artificial neural networks, this is typically accomplished b…
Continual learning with the neural tangent ensemble
Ari S. Benjamin, Christian Pehle, Kyle Daruwalla
A natural strategy for continual learning is to weigh a Bayesian ensemble of fixed functions. This suggests that if a (single) neural network could be interpreted as an ensemble, o…
jaxsnn: Event-driven Gradient Estimation for Analog Neuromorphic Hardware
Eric Müller, Moritz Althaus, Elias Arnold +3
Traditional neuromorphic hardware architectures rely on event-driven computation, where the asynchronous transmission of events, such as spikes, triggers local computations within…
Emulating insect brains for neuromorphic navigation
Korbinian Schreiber, Timo Wunderlich, Philipp Spilger +8
Bees display the remarkable ability to return home in a straight line after meandering excursions to their environment. Neurobiological imaging studies have revealed that this capa…
Gradient-based methods for spiking physical systems
Julian Göltz, Sebastian Billaudelle, Laura Kriener +5
Recent efforts have fostered significant progress towards deep learning in spiking networks, both theoretical and in silico. Here, we discuss several different approaches, includin…
Event-based Backpropagation for Analog Neuromorphic Hardware
Christian Pehle, Luca Blessing, Elias Arnold +2
Neuromorphic computing aims to incorporate lessons from studying biological nervous systems in the design of computer architectures. While existing approaches have successfully imp…
hxtorch.snn: Machine-learning-inspired Spiking Neural Network Modeling on BrainScaleS-2
Philipp Spilger, Elias Arnold, Luca Blessing +4
Neuromorphic systems require user-friendly software to support the design and optimization of experiments. In this work, we address this need by presenting our development of a mac…
Using Forwards-Backwards Models to Approximate MDP Homomorphisms
Augustine N. Mavor-Parker, Matthew J. Sargent, Christian Pehle +3
Reinforcement learning agents must painstakingly learn through trial and error what sets of state-action pairs are value equivalent -- requiring an often prohibitively large amount…
A Scalable Approach to Modeling on Accelerated Neuromorphic Hardware
Eric Müller, Elias Arnold, Oliver Breitwieser +20
Neuromorphic systems open up opportunities to enlarge the explorative space for computational research. However, it is often challenging to unite efficiency and usability. This wor…
The BrainScaleS-2 accelerated neuromorphic system with hybrid plasticity
Christian Pehle, Sebastian Billaudelle, Benjamin Cramer +7
Since the beginning of information processing by electronic components, the nervous system has served as a metaphor for the organization of computational primitives. Brain-inspired…
Event-Based Backpropagation can compute Exact Gradients for Spiking Neural Networks
Timo C. Wunderlich, Christian Pehle
Spiking neural networks combine analog computation with event-based communication using discrete spikes. While the impressive advances of deep learning are enabled by training non-…
hxtorch: PyTorch for BrainScaleS-2 -- Perceptrons on Analog Neuromorphic Hardware
Philipp Spilger, Eric Müller, Arne Emmel +10
We present software facilitating the usage of the BrainScaleS-2 analog neuromorphic hardware system as an inference accelerator for artificial neural networks. The accelerator hard…
Surrogate gradients for analog neuromorphic computing
Benjamin Cramer, Sebastian Billaudelle, Simeon Kanya +9
To rapidly process temporal information at a low metabolic cost, biological neurons integrate inputs as an analog sum but communicate with spikes, binary events in time. Analog neu…
Neuromorphic quantum computing
Christian Pehle, Christof Wetterich
We propose that neuromorphic computing can perform quantum operations. Spiking neurons in the active or silent states are connected to the two states of Ising spins. A quantum dens…
Closed-loop experiments on the BrainScaleS-2 architecture
K. Schreiber, T. C. Wunderlich, C. Pehle +3
The evolution of biological brains has always been contingent on their embodiment within their respective environments, in which survival required appropriate navigation and manipu…
Versatile emulation of spiking neural networks on an accelerated neuromorphic substrate
Sebastian Billaudelle, Yannik Stradmann, Korbinian Schreiber +22
We present first experimental results on the novel BrainScaleS-2 neuromorphic architecture based on an analog neuro-synaptic core and augmented by embedded microprocessors for comp…
Neuromorphic Hardware learns to learn
Thomas Bohnstingl, Franz Scherr, Christian Pehle +2
Hyperparameters and learning algorithms for neuromorphic hardware are usually chosen by hand. In contrast, the hyperparameters and learning algorithms of networks of neurons in the…
Demonstrating Advantages of Neuromorphic Computation: A Pilot Study
Timo Wunderlich, Akos F. Kungl, Eric Müller +14
Neuromorphic devices represent an attempt to mimic aspects of the brain's architecture and dynamics with the aim of replicating its hallmark functional capabilities in terms of com…
Emulating quantum computation with artificial neural networks
Christian Pehle, Karlheinz Meier, Markus Oberthaler +1
We demonstrate, that artificial neural networks (ANN) can be trained to emulate single or multiple basic quantum operations. In order to realize a quantum state, we implement a nov…
An Accelerated LIF Neuronal Network Array for a Large Scale Mixed-Signal Neuromorphic Architecture
Syed Ahmed Aamir, Yannik Stradmann, Paul Müller +5
We present an array of leaky integrate-and-fire (LIF) neuron circuits designed for the second-generation BrainScaleS mixed-signal 65-nm CMOS neuromorphic hardware. The neuronal arr…
Chow groups, Deligne cohomology and massless matter in F-theory
Martin Bies, Christoph Mayrhofer, Christian Pehle +1
We propose a method to compute the exact number of charged localized massless matter states in an F-theory compactification on a Calabi-Yau 4-fold with non-trivial 3-form data. Our…